Adaptive dual prediction scheme based on sensing context similarity for wireless sensor networks

Abstract

A novel adaptive dual-prediction scheme is introduced for minimising the data communication load for wireless sensor networks as a way to maximise the lifetime of resource-limited sensor nodes. Specifically, the proposed scheme exposes the fact that when sensing context prediction is used at both the sink node and the sensor nodes, the amount of data that need to be transmitted can be minimised. Furthermore, the transmission data quantity is reduced even more by exploiting the spatial correlation among different sensor nodes. On using this adaptive dual prediction scheme, the evaluations show that the amount of data transmissions can be compressed by as much as 20% against a basic dual prediction scheme, suggesting that the lifetime of sensor nodes can increase significantly in practical systems.